1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-18 02:10:12 +01:00
searxng/searx/engines/bing.py

50 lines
1.6 KiB
Python
Raw Normal View History

2013-10-24 23:52:57 +02:00
from urllib import urlencode
from cgi import escape
2014-02-05 20:24:31 +01:00
from lxml import html
2013-10-24 23:52:57 +02:00
base_url = 'http://www.bing.com/'
2014-01-29 21:14:38 +01:00
search_string = 'search?{query}&first={offset}'
paging = True
2014-01-31 04:35:23 +01:00
language_support = True
2014-01-29 21:14:38 +01:00
2013-10-24 23:52:57 +02:00
def request(query, params):
2014-01-29 21:14:38 +01:00
offset = (params['pageno'] - 1) * 10 + 1
2014-01-31 04:35:23 +01:00
if params['language'] == 'all':
language = 'en-US'
else:
language = params['language'].replace('_', '-')
search_path = search_string.format(
2014-01-31 04:35:23 +01:00
query=urlencode({'q': query, 'setmkt': language}),
2014-01-29 21:14:38 +01:00
offset=offset)
2014-01-31 04:35:23 +01:00
params['cookies']['SRCHHPGUSR'] = \
'NEWWND=0&NRSLT=-1&SRCHLANG=' + language.split('-')[0]
2013-10-24 23:52:57 +02:00
#if params['category'] == 'images':
# params['url'] = base_url + 'images/' + search_path
params['url'] = base_url + search_path
return params
def response(resp):
global base_url
results = []
dom = html.fromstring(resp.content)
for result in dom.xpath('//div[@class="sa_cc"]'):
link = result.xpath('.//h3/a')[0]
url = link.attrib.get('href')
title = ' '.join(link.xpath('.//text()'))
content = escape(' '.join(result.xpath('.//p//text()')))
results.append({'url': url, 'title': title, 'content': content})
2013-10-25 01:37:48 +02:00
if results:
return results
for result in dom.xpath('//li[@class="b_algo"]'):
link = result.xpath('.//h2/a')[0]
url = link.attrib.get('href')
title = ' '.join(link.xpath('.//text()'))
content = escape(' '.join(result.xpath('.//p//text()')))
results.append({'url': url, 'title': title, 'content': content})
2013-10-24 23:52:57 +02:00
return results